Publications (12)
Societal Alignment Frameworks Can Improve LLM Alignment
Karolina StaÅczak, Nicholas Meade, Mehar Bhatia +14
Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment. However,…
From Distances to Trajectories: Real-Time Signed Distance Function Mapping and Distance-Accelerated Motion Planning for UAVs
Jason Stanley, Zhirui Dai, Qihao Qian +6
Autonomous flight in cluttered environments requires a robot to build a geometric map of its surroundings and plan safe, dynamically feasible trajectories, all onboard and in real…
Port-Hamiltonian Neural ODE Networks on Lie Groups For Robot Dynamics Learning and Control
Thai Duong, Abdullah Altawaitan, Jason Stanley +1
Accurate models of robot dynamics are critical for safe and stable control and generalization to novel operational conditions. Hand-designed models, however, may be insufficiently…
Active Diagnosis via AUC Maximization: An Efficient Approach for Multiple Fault Identification in Large Scale, Noisy Networks
Gowtham Bellala, Jason Stanley, Clayton Scott +1
The problem of active diagnosis arises in several applications such as disease diagnosis, and fault diagnosis in computer networks, where the goal is to rapidly identify the binary…
DoomArena: A framework for Testing AI Agents Against Evolving Security Threats
Leo Boisvert, Mihir Bansal, Chandra Kiran Reddy Evuru +9
We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a plug-in framework and integrates easily into realistic ag…
Learned IMU Bias Prediction for Invariant Visual Inertial Odometry
Abdullah Altawaitan, Jason Stanley, Sambaran Ghosal +2
Autonomous mobile robots operating in novel environments depend critically on accurate state estimation, often utilizing visual and inertial measurements. Recent work has shown tha…
Hamiltonian Dynamics Learning from Point Cloud Observations for Nonholonomic Mobile Robot Control
Abdullah Altawaitan, Jason Stanley, Sambaran Ghosal +2
Reliable autonomous navigation requires adapting the control policy of a mobile robot in response to dynamics changes in different operational conditions. Hand-designed dynamics mo…
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Umang Bhatt, Javier Antorán, Yunfeng Zhang +12
Algorithmic transparency entails exposing system properties to various stakeholders for purposes that include understanding, improving, and contesting predictions. Until now, most…
LitLLMs, LLMs for Literature Review: Are we there yet?
Shubham Agarwal, Gaurav Sahu, Abhay Puri +5
Literature reviews are an essential component of scientific research, but they remain time-intensive and challenging to write, especially due to the recent influx of research paper…
LitLLM: A Toolkit for Scientific Literature Review
Shubham Agarwal, Gaurav Sahu, Abhay Puri +5
Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work. It is a tedious task which makes an aut…
Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
Léo Boisvert, Léo Boisvert, Abhay Puri +8
While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the a…
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
Joshua Kazdan, Abhay Puri, Rylan Schaeffer +5
Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to…